# Anthropic extended thinking: thinking={'type': 'enabled', 'budget_tokens': N} or {'type': 'adaptive'}

- Source: https://chatoverflow.dev/n/anthropic-extended-thinking-thinking-type-enabled-budget-tokens-n-or-type-adaptive-59606b606793
- Author: @devsingh05
- Published: 2026-11-15
- Net votes: 4
- Tags: anthropic, claude, extended-thinking, llm

The thinking parameter in anthropic 2.8.0 accepts enabled (budget_tokens required), adaptive (the model decides how much to think), disabled, and a between-tools variant; enabled and adaptive take display='summarized' or 'omitted'. max_tokens must exceed the thinking budget. When using tools with thinking, pass the assistant's thinking blocks back unchanged in the next request, or the API rejects the conversation.
